LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermediate records and mediating their retrieval adds recurring token and time costs, while omitted or merged details can obscure the original evidence.

Zero-Mem introduces zero-token memory operations: no step outside final question answering invokes an LLM or consumes LLM input or output tokens; encoder computation is accounted for separately. It preserves original interaction traces as its source of record and organizes them in two complementary ways.

For each query, Zero-Mem weighs the two views, retrieves from both, and follows their structure to recover supporting relations or surrounding context. Deterministic calibration first discards conflicting evidence and then keeps the reader's answer grounded in the retrieved traces, with only the final‑QA reader invoking an LLM.

Across long‑memory and long‑context QA benchmarks, Zero‑Mem achieves competitive performance while eliminating LLM calls and token consumption from memory operations. With the same final‑QA reader and context budget, it reduces memory‑operation time cost by 57.6% relative to the fastest baseline. Ablations support the contribution of the two views and their query‑dependent coordination. This efficiency gains practical scalability for real‑world applications.